A Microgrid Energy Management System Based on Non-Intrusive Load Monitoring via Multitask Learning

Non-intrusive load monitoring (NILM) enables to understand the appliance-level behavior of consumers by using only smart meter data, and it mitigates requirements such as high-cost sensors, maintenance/update provides a cost-effective solution. This article presents an efficient NILM-based energy management system (EMS) for residential microgrids. Firstly, data are analyzed with multi-task deep neural network-based approach information is extracted. Both consumption operating status appliances obtained. Afterward, behaviors end-users these data. Accordingly, average power consumption, operation cycles, preferred usage periods, daily frequency were obtained accuracy more than 90%. The results integrated into EMS create user-centered microgrid operation. developed model not provided optimum dispatch distributed generation plants in but also scheduled controllable loads taking account customers' satisfaction. It was demonstrated help simulation that proposed improves cost/customer satisfaction ratio between 45% 65% compared traditional EMS.